One model is tracked on MMAU (Speech): Qwen2.5 Omni 7B at 59.8.
Data as of August 23, 2026MMAU (Massive Multi-task Audio Understanding), Speech subset — Distinct submetric within MMAU (Tencent, 9 models); range excludes the MMAU* point -- kept separate.
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Qwen2.5 Omni 7B | Alibaba | 59.8 | 1 | 2026-08-23 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.